Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 90 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. Free open-weight models included. Also exposes realtime market data (global stocks, crypto, FX, commodities), Twitter/X intelligence, prediction-market data across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow + UMA oracle resolution + wallet identity & clustering, phone-number intelligence (carrier + SIM-swap fraud detection) plus AI-powered outbound voice calls (Twilio + Bland.ai) as built-in agent tools. Not a local-inference tool — prompts are sent to the blockrun.ai gateway.
Build or refactor agent-facing CLI tools with non-interactive commands, stable --help and --json contracts, idempotent operations, and --dry-run previews. Use for CLI design, agent-friction refactors, output/exit-code debugging, or automation safety. Do not use for GUI/TUI design, conversational tools, MCP server design, or general API architecture; use api-design-and-evolution for the latter.
Use when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and fuzzy/semantic search; anchoring LSP calls by position; gating degraded results; and disclosing tool substitutions, in any language.
Explicit-only last resort. Draws game art from code, with no image model - pixel sprites from a PixelSpec, flat vector props, UI and icons from portable SVG, rigged characters with planted feet, FX with a JS runtime, seam-proven autotiles, playable top-down layouts with collision, stylized parallax and ambient plate motion - palette-exact, with QA and review sheets. Use only when the user explicitly asks for code-drawn art, or when generate2dmedia route_media.py finds no image or video route (no-route, exit 3). Never the default - image generation (generate2dsprite, generate2dmap, video2dsprite) comes first for characters, props, maps and FX. Not for painterly, detailed or likeness art, HD-2D plates or realistic fire, smoke or water. Always disclose the result as code-drawn.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module interface, find deepening opportunities, decide where to put a seam, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Production patterns for building customer-facing storefronts on commercetools - the full B2C and B2B domain feature set. Patterns are stated as decisions plus commercetools-exact code; framework-specific implementation. Assumes a server tier exists to host the BFF. Use for PDP, PLP, cart, checkout flow, customer login, search/facets, locale handling, and any B2B- or B2C-specific feature.
Tailors Codacy configuration to a project by discovering its stack, enabling the right tools and patterns, running analysis, and intelligently reducing noise — disabling irrelevant or noisy patterns, tuning thresholds, and excluding files that shouldn't be analyzed. Produces a machine-readable summary of all changes. Use whenever the user wants to configure Codacy, reduce noise, fix false positives, enable or disable tools or patterns, tune code quality rules, deal with too many warnings, or align Codacy with their project's conventions. Also trigger when the user complains about irrelevant issues, noisy linters, or wants to set up Codacy for the first time on a repo.
Apply consulting methodologies from McKinsey, BCG, Bain, and Accenture for structured problem-solving and strategic analysis. Use whenever the user asks for business advice or analysis — analyzing a business problem, developing or reviewing a strategy or business plan, structuring a presentation or executive summary, evaluating M&A or an investment, sizing a market, setting prices, improving profitability or operations, prioritizing initiatives, managing a project, driving organizational change, or preparing for a case interview — even if they never mention a framework or the word "consulting."
Reviews your last 30 posts to find what is worth doubling down on, what is dead weight, and the gaps to fill. Use when the user says "audit my content", "what is working on my account", "what should I stop posting", "review my last 30 posts".
Review the contract/agreement provided by the user for risky clauses, generate review opinions, and return the annotated reviewed contract document. Triggered when the user mentions document review, contract review, contract risk scanning, risk checks, clause checks, or doubts about contract content. (Trigger phrases: are there problems with the clauses, review the XXX contract, help me look at the risks of this agreement, are these contract terms unfavorable to me, etc.)
Sweep a contracts folder and extract every renewal date, auto-renew clause, notice window, and price-escalation term into a renewal calendar -- then create calendar reminders ahead of each notice deadline via Cowork's calendar write tools. The skill that stops auto-renewals from ambushing you.
Point Cowork at a folder of medical bills and insurance EOBs -- matches every bill to its explanation of benefits, catches duplicate charges, balance-billing, and bills that ignore your insurance, then drafts the dispute letters and phone scripts. Most medical bills contain errors; this finds them.
Build a quarterly business review from a client folder -- reports, usage exports, support tickets, meeting notes, emails. Extracts delivered value with receipts, surfaces risks before the client does, and drafts the QBR narrative plus expansion asks. For agencies, consultancies, and CS teams.
Use when the user asks to create a GitHub issue, file a bug, request a feature, open a tracking issue, or break a feature into multiple sub-issues. Guides interactive issue drafting with structured templates, workspace-change attachment, dependency linking, and the optional `autonomous` label for the automated dev pipeline.
Deep research methodology (8-step method): turn a vague topic into a high-quality research report. Trigger words: /deep-research, deep research, help me research, look into this, comparative analysis. Note: if the user needs a visualization or diagram rather than a report, use the research-to-diagram skill.
Guide for implementing DefectDojo - an open-source DevSecOps, ASPM, and vulnerability management platform. Use when querying vulnerabilities, managing findings, configuring CI/CD pipeline imports, or working with security scan data. Includes MCP tools for direct API interaction.
Interview employees to identify recurring daily work, office workflows, and repetitive tasks that can be automated, co-piloted, or supported by AI. Use when the user wants to find what AI can take off their plate, map available tools such as ChatGPT/OpenAI, Claude, Microsoft Copilot, Excel or PowerPoint add-ins, Google Workspace, no-code/RPA tools, coding agents, or internal automation platforms, and write tool-aware specs with fallback paths.
Structured design critique using the Liz Lerman Critical Response Process, plus deep-dives on Stripe, Linear, Notion, Airbnb, Figma, and Arc, and post-mortems of redesign failures like Snapchat 2018 and Sonos 2024. Use when running a critique session, giving design feedback, or learning from a shipped product.
Install a complete design-token theme into any project in one pass -- pulls a style from the Open Agent Stack design-styles collection (aurora-mesh, cirrus, liquid-glass, mono-brutalist, neo-terminal, sand-terra, tidal) or a local tokens.json, wires it into Tailwind/CSS, and repaints existing components to match.
Anti-slop design skill for landing pages, portfolios, and marketing sites. The agent reads the brief, infers a deliberate design direction, and ships interfaces that do not look AI-generated. Ban the LLM defaults, set typography and color deliberately, run the pre-flight checklist before finishing
Official document formatting tool. Automatically formats doc/docx/wps/txt/md documents according to official document formatting conventions and outputs standard docx. Supports intelligent recognition of heading levels (一、/（一）/1./（1）), titles/subtitles, attachment formatting, chart caption recognition, page margins, page numbers, line spacing, fonts and font sizes, TXT/MD blank-line modes, custom configuration, and batch processing of directories. Use this skill when the user needs to compose official documents, format documents, unify document formats, or adjust fonts, font sizes, line spacing, and margins. Keywords: official document formatting, document formatting, font settings, heading levels, format unification, formatting tool.
Adds .NET Aspire cloud-native orchestration to existing .NET solutions. Analyzes solution structure to identify services (APIs, web apps, workers), creates AppHost and ServiceDefaults projects, configures service discovery, adds NuGet packages, and sets up distributed application orchestration. Use when adding Aspire to .NET solutions or creating new cloud-ready distributed applications.
Verifies API implementations against OpenAPI specifications using the Drift CLI, catching spec drift and supporting Bi-Directional Contract Testing (BDCT). Use when the user mentions Drift, API contract testing, provider contract testing, provider verification, spec drift, API conformance testing, OpenAPI verification, BDCT, drift expressions, drift datasets, drift lifecycle hooks, or Lua scripting in a testing context. Use when the user asks to write, run, or debug Drift test cases. Use when the user wants to test their API against an OpenAPI spec, generate tests from an OpenAPI spec, or check whether their API has drifted from its spec. Use when the user wants full endpoint coverage, wants all tests to pass, or asks to "keep running until everything passes". Also use when the user mentions AsyncAPI, event-driven API testing, Kafka contract testing, SNS or SQS testing, async message contracts, or wants to verify that a service publishes or consumes messages matching an AsyncAPI spec. Also use when the user mentions MCP, Model Context Protocol, MCP server testing, `.mcp.yaml` definitions, or verifying an MCP server's tools, resources or prompts.
Optimize DSPy programs with dspy.GEPA — a reflective/evolutionary optimizer to consider against task-specific baselines within an authorized evaluation budget. Use when the user says optimize, compile, GEPA, reflective optimization, or "make this program better" and a DSPy program + metric + trainset exist.
Set up, manage, and troubleshoot recurring loops on a duoduo install — the /loop command and the background jobs it creates. Use when the user wants duoduo to do something repeatedly or on a schedule, watch something until it finishes, run a long-term tracker, or inspect/stop/pause/re-pace/interrupt an existing loop. Also trigger for Chinese: 定时任务, 循环任务, 周期任务, 每天帮我, 每小时, 盯着…直到, 持续跟进, 长期跟踪, 看看我的循环, 停掉那个 loop, 暂停循环, 改一下节奏, 打断卡住的那一轮, 让多多定期做某事.
Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack. Use this skill whenever someone wants to understand where they're spending their management energy, find blind spots, get a monthly self-reflection on their EM focus, or hear phrases like "score my EM grid", "where am I spending time as a manager", "what are my blind spots", "analyze my calendar as EM", "which EM areas am I neglecting", "how balanced is my management focus", or "check my EM grid coverage". Always pull live calendar data — never ask the user to describe their week manually.
During development, save a very brief clue when encountering a non-obvious failure, user correction, or repetitive operation that could be automated. Don’t interrupt the main task or search for evidence; don’t write anything to disk for pure consultation or read-only tasks. Leave deeper investigation to agi-mode retrospectives.
Provides comprehensive guidance for Express.js framework including routing, middleware, request handling, error handling, and API development. Use when the user asks about Express, needs to create HTTP servers, set up routes, implement middleware, or build REST APIs.
Comprehensive guide for configuring, troubleshooting, and implementing External-DNS across Azure DNS, AWS Route53, Cloudflare, and Google Cloud DNS. Use when implementing automatic DNS management in Kubernetes, configuring provider-specific authentication (managed identities, IRSA, API tokens), troubleshooting DNS synchronization issues, setting up secure production-grade external-dns deployments, optimizing performance, avoiding rate limits, or implementing GitOps patterns with ArgoCD.
Felo SuperAgent API: AI conversation with real-time SSE streaming on a persistent LiveDoc canvas. Use when users want SuperAgent chat, continuous conversation, logo/branding design, or e-commerce product images. Do NOT use for tweet/X post writing — use felo-twitter-writer instead. Explicit commands: /felo-superAgent.
Complete glitch art, datamosh, and video distortion effects system. PROACTIVELY activate for: (1) Datamosh/pixel bleeding effects, (2) VHS/analog glitch simulation, (3) Digital corruption effects, (4) Displacement mapping, (5) Wave/ripple distortions, (6) Pixelation and mosaic effects, (7) Chromatic aberration, (8) Scan line effects, (9) Time-based distortions (echo, trails), (10) Lens distortion and barrel effects. Provides: minterpolate for datamosh, displacement filter, geq pixel manipulation, noise and artifacts, rgbashift/chromashift for color separation, lagfun for trails, tmix for frame blending, tblend for frame difference effects.
Find web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or finding structured records, listings, transcripts, and datasets. Supports semantic tool discovery, domain matching, and progressive catalogue browsing.
Helps a paper hit its target length: recommends exactly what to compress when it is over the page limit, or what to add with substance when it is too short. Use when a researcher says "I'm over the page limit", "compress my paper", "what should I cut", "trim two pages", "my paper is too long", "help me fit NeurIPS's limit", "my paper is too short", "I have space left, what should I add", or "where is all my length going". Runs a section-by-section length analysis, then gives a prioritized, value-aware plan: which low-value sections to condense or move to an appendix, while protecting contributions, results, and citations, or which thin sections to develop. Never deletes evidence to fit and never pads to fill. Trigger words: page limit, compress, trim, cut down, too long, too short, over the limit, fit the limit, what to cut, what to add.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.